Run Gemini CLI on Your Phone (iPhone + Android)

You can run Google Gemini CLI on your phone today, iPhone or Android. The fastest path: install Cosyra for iOS or Cosyra for Android, sign in, and type gemini in the terminal. We pre-install Gemini CLI in an Ubuntu 24.04 container in the cloud, so there is no Node 20 install, no Termux native-build errors, no SSH tunnel to babysit. Heads up before you start: Gemini CLI's free personal-account tier ended 2026-06-18, so you now authenticate with a paid Google AI Studio or Vertex API key. 1 hour free on Cosyra signup, no credit card. On Android specifically, where Termux is a real on-device option, our Gemini CLI on Android guide goes deeper on the NDK build failures, the workarounds, and the phantom-process killer. On iPad it's a different story — there is no Termux, and the on-device shells can't run Node — so our Gemini CLI on iPad guide covers the two paths that actually work on the tablet. The iPhone hits the same iOS wall in a one-handed form factor, which our Gemini CLI on iPhone guide walks through with dictation and the commute-kickoff workflow.

This guide was written by the Cosyra team. We tested Gemini CLI on iPhone and Android via Cosyra, plus the Termux path and the Blink-plus-VPS path. Where we make claims about Gemini CLI itself, they are re-verified 2026-06-23 and cross-checked against the official repo and the Google announcement.

What is Google Gemini CLI?

Gemini CLI is Google's official open-source terminal agent for the Gemini models. The README calls it "an open-source AI agent that brings the power of Gemini directly into your terminal." It ships under Apache 2.0, as the @google/gemini-cli npm package, and also installs via Homebrew, MacPorts, and Anaconda. It needs Node.js 20 or newer. Features include file operations, shell command execution, web search, and tool extensibility via MCP (Model Context Protocol) — the same protocol whose servers we keep alive in a cloud container so a backgrounded phone app cannot kill them, walked through in running MCP servers from your phone.

Until 2026-06-18, the thing that made Gemini CLI genuinely different from Claude Code or Codex CLI on a phone was the free-tier economics: a personal Google account, no API key, no credit card, and 60 requests per minute and 1,000 per day across the Gemini model family with Gemini 2.5 Flash as the default. Google positioned the allowance as "the industry's largest" for unpaid access when they launched. That free path is gone now — the sign-in returns HTTP 410 Gone. What remains is the same Apache-2.0 binary running on a paid AI Studio or Vertex key, where Gemini 2.5 Pro's 1-million-token context window is still the draw — larger than most competitors' defaults, and cheap on Flash for a quick large-context pass even though it is no longer free.

How can you run Gemini CLI on a phone?

You can run Gemini CLI on a phone three ways: a cloud Ubuntu container with Gemini pre-installed reached from a native mobile app (Cosyra), Termux on Android with install workarounds, or Blink Shell on iOS into a VPS you own. Gemini CLI needs a real Linux or macOS shell with Node 20+, so every approach puts the actual CLI process somewhere else and gives your phone a way to drive it. All three options are current as of 2026-06-23.

1. Cosyra: cloud Ubuntu container, Gemini CLI pre-installed

This is what we built. A native iOS and Android terminal that connects to a persistent Ubuntu 24.04 container in the cloud. Gemini CLI, Claude Code, Codex CLI, and OpenCode are already installed against a current Node 20+. You paste a paid GEMINI_API_KEY (the free Google sign-in ended 2026-06-18), type gemini, and go.

• Works when: you want zero setup, dual-platform (iOS and Android), and none of the Termux native-build pain that recent Gemini CLI releases have.
• Breaks when: you have no internet (the container lives in the cloud), or you need to reach a private network we do not route through. Full trade-off list in Cosyra vs Termux.
• Cost: 1 hour free on signup, no credit card. Extend with a 10-hour, 7-day trial when you want more. After that, $29.99/month or $300/year. Gemini model usage is BYOK via a paid AI Studio or Vertex AI key — the free 60 rpm / 1000 rpd personal-Google tier ended 2026-06-18. See pricing.

2. Termux on Android, with install workarounds

Install Termux from F-Droid, install Node 20+ with pkg install nodejs, then npm install -g @google/gemini-cli. On paper this should work. In practice, the google-gemini/gemini-cli repo has a string of open and closed Termux issues: 0.3.3 failed on Termux with Node v22.19.0, 0.11.0-nightly failed to build on Termux/arm64 with Node v24, and a separate clipboardy mis-detection bug was closed by Google as "not planned." The two working recipes today are (a) add --ignore-scripts so native modules like tree-sitter-bash are not built, or (b) pin an older version such as @google/gemini-cli@0.2.2. A community fork, DioNanos/gemini-cli-termux, exists specifically because the upstream path is brittle on Android.

• Works when: you are on Android, you know your way around pkg, and you accept the version-pinning tax.
• Breaks when: a Gemini CLI release drops that needs a newer native dep; you upgrade; the app breaks until a workaround catches up. Also Android 12+'s phantom process killer can terminate long sessions.
• Cost: free Termux, but Gemini model usage now needs a paid AI Studio/Vertex key (the free personal tier ended 2026-06-18). The bigger cost is the time you spend debugging install failures vs. shipping code.

3. SSH from Blink Shell into your own VPS (iOS only)

On iPhone or iPad, Blink Shell is the gold-standard SSH client. Spin up a VPS (Hetzner, Scaleway, DigitalOcean), npm install -g @google/gemini-cli on it, SSH in from Blink inside a tmux session, and run gemini. Authentication via GEMINI_API_KEY is the simplest path here because browser-flow sign-in is awkward over SSH.

• Works when: you want a box that is yours and an iOS-native keyboard. Polished terminal UX on iPhone.
• Breaks when: you do not want to be a sysadmin. Patching, hardening, firewall rules, and backups are not optional on a box that holds your source code and your Gemini API key.
• Cost: Blink Shell is $19.99/year, the VPS is $5 to $40/month. No Android equivalent, Blink is iOS-only. Full trade-off breakdown in Blink Shell alternative: Cosyra for iPhone terminals.

How do you set up Gemini CLI on iPhone or Android?

You set up Gemini CLI on iPhone or Android in about three minutes with Cosyra: install the app, sign in, confirm gemini is on the PATH, paste a paid GEMINI_API_KEY (the free Google sign-in ended 2026-06-18), clone a repo, run gemini. No Node install, no npm, no Termux native-build errors.

Step 1: Install Cosyra and sign in

Download from the App Store or Google Play. Sign in with Apple, Google, or email. On first launch we provision a fresh Ubuntu 24.04 container.

Step 2: Confirm Gemini CLI is there

No install step — Gemini CLI is baked into the image. Verify in one command.

Step 3: Authenticate with a paid Gemini API key

The personal-Google-account free tier (60 rpm / 1,000 rpd) ended 2026-06-18, so the free browser sign-in no longer works — it returns HTTP 410 Gone. The working path now is a paid key: grab one from Google AI Studio or Vertex AI, export it, and run gemini. Gemini 2.5 Flash is the cheapest model and stays inexpensive for casual phone use; gemini-2.5-pro unlocks the 1-million-token context window at a higher per-token cost.

Step 4 (optional): Or move to Antigravity CLI

If you would rather stay on Google's free-of-subscription path, Antigravity CLI (agy) is the official replacement for the retired free tier. Google has not published a free-request quota for it, so confirm the limits in Google's transition note before you rely on it. For most phone workflows, a paid Flash key on the Apache-2.0 gemini binary is the lower-friction choice.

Step 5: Run your first Gemini prompt

Gemini reads the repo, summarizes it, and lists long files. You see the result on your phone screen. The 1M-token context window means it can ingest a lot of code in one pass, useful when you are triaging a repo you have not touched in months.

What can you actually do with Gemini on your phone?

The unlock on a phone is specifically Gemini 2.5 Pro's 1-million-token context window: you can paste or reference a large amount of code in one prompt and still get a coherent answer. Since the free personal tier ended 2026-06-18, you run this on a paid AI Studio/Vertex key — Flash for cheap everyday passes, Pro when you need the full context window. Three real sessions we run from a phone.

Triage a large repo on the train

You inherited a service with 40 files you have never read. Open Cosyra, cd in, run gemini, type "summarize what this service does, its public API, and the three riskiest files." The 1M-token window means Gemini can look at most of the codebase in one pass on a moderate service. You get an overview before your stop.

Generate tests for a module from the couch

Saturday morning. Pick a file that needs tests. "Read src/billing/invoice.ts and write a Vitest suite covering the three pricing tiers and the proration edge cases." Gemini proposes the test file, you review, approve, run.

Explain a third-party library when you are stuck

Pager does not need to be going off. Sometimes you just want to understand what a hairy library does before you commit to using it. Paste its README into gemini with "explain the mental model I should have before I use this." Gemini's 1M context is enough to take the whole README plus a couple of example files in a single Flash request.

What are the real limits of running Gemini CLI on a phone?

The real limits are no offline mode, paid-key billing now that the free personal tier has ended, Gemini 2.5 Pro is not always the best model for every task, and Google's terms can change on short notice. Knowing where Gemini stops helps you match it to the right job instead of fighting it.

• No offline mode. The container and the Gemini API both live in the cloud. No internet, no Gemini. If you code on planes with no wifi, this is not the right tool for that slot.
• Paid-key billing. Since the free personal tier ended 2026-06-18, every request bills against your AI Studio/Vertex key. Flash is cheap for interactive use; a long autonomous agent run firing dozens of tool calls in sequence on Pro adds up, so watch the model you select.
• Gemini 2.5 Pro is not always the right model. For deep code reasoning we often prefer Claude Code. For iterative shell work we often prefer Codex. We use Gemini specifically for large-context ingestion tasks and research-style summaries. For the direct Anthropic-vs-Google head-to-head on phone — including how the 2026-06-18 sunset reshaped the cost picture — see Claude Code vs Gemini CLI on phone. For the broader four-agent picture, see our AI coding agents on mobile pillar.
• The free tier has been retired. The 60 rpm / 1000 rpd family-wide numbers applied through 2026-06-17, but Google announced on 2026-05-20 that Gemini CLI is being replaced by Antigravity CLI, and on 2026-06-18 it stopped serving requests for free individual, Google AI Pro, and Ultra users. Set up a BYOK Gemini API key, or move to Antigravity CLI.
• No Docker-in-Docker guarantee inside the container. If your project's tests need docker, verify before committing to phone-only.

How does Cosyra compare to Termux and Blink+VPS for Gemini CLI?

Cosyra wins for zero-setup, dual-platform use, and skipping the Termux native-build drama; Termux wins if you are an Android power user who accepts the pinning tax; Blink plus a VPS wins on iOS if you want a box you own. None is strictly best; each maps to a trade-off. Comparison as of 2026-05-21.

For the broader picture across all four AI agents on mobile, see our pillar guide on AI coding agents on mobile. For the same walkthrough with Anthropic's tool, see Claude Code on phone; for OpenAI's, see Codex CLI on phone; for the open-source alternative that lets you swap models without rewriting your config, see OpenCode on phone. If you want the Gemini CLI fork built around Alibaba's open-weight model, see Qwen Code on phone or the head-to-head Cosyra vs Qwen Code comparison. For Google's other mobile dev surface — the hosted Firebase Studio workspace rather than the CLI — see how the same workspace holds up on a phone-sized Safari window in Firebase Studio on phone and on an iPad in Firebase Studio on iPad. Gemini CLI is the interactive Google agent you drive live in the shell; for its async sibling that runs in a cloud VM and hands you a pull request instead of a session, see Jules on your phone — or, if you drive that agent from a tablet, Jules on iPad, or weigh the two approaches head-to-head in Cosyra vs Jules. For the AWS equivalent — a terminal agent that logs in with an AWS Builder ID instead of a provider key you paste — see Amazon Q CLI on your phone.

Frequently asked questions